Population global optimization method for regional dynamic subdivision based on local Lipschitz estimation

Abstract

Provided is a population global optimization method for regional dynamic subdivision based on local Lipschitz estimation. The population global optimization method is combined with the Lipschitz estimation theory under the framework of a population evolutionary algorithm and comprises the steps of constructing a Lipschitz estimation lower bound bearing surface by extracting neighborhood information of new individuals to achieve dynamic subdivision of a search region; effectively identifying part of an invalid region by means of lower bound estimation information and guiding population update; performing local reinforcement by means of the general declining direction of a linear fit convex envelope, and performing secondary subdivision on the search region according to evolution information; reinitializing part of poor individuals in a population according to lower bound estimation selection information. The population global optimization method for regional dynamic subdivision based on local Lipschitz estimation is low in computing cost, and high in rate of convergence and reliability.

Description

technical field [0001] The invention relates to the field of intelligent optimization and computer application, in particular to a global optimization method for regional dynamic subdivision groups based on local Lipschitz estimation. Background technique [0002] In practical engineering applications, many optimization problems often need to quickly obtain a certain global optimal solution of the problem. Gradient-based quasi-Newton method, conjugate gradient method and other traditional methods, as well as direct search methods such as Nelder-Mead and Hooke-Jeeves are essentially a kind of local search method, the quality of the solution directly depends on the selection of the starting point, for some For complex optimization problems, it is basically impossible for these methods to obtain the global optimal solution of the problem. [0003] The deterministic algorithm approximates the objective function by constructing a lower bound convex envelope that is continuously ...

AI Technical Summary

Problems solved by technology

The differential evolution algorithm (DE) proposed by Storn et al. solves the optimization problem through the cooperation and competition among individuals in the population. The application solution of the problem shows its unique advantages, but it also exposes many shortcomings and defects in theory and application, such as high calculation cost (such as the number of function evaluations), slow convergence speed in the later stage, and it is easy to tend to premature convergence But trapped in a local optimal solution, the reliability is low

[0005] Therefore, the existing global optimization methods have defects in calculation cost, convergence speed and reliability, and need to be improved.

Images